[USER (data scientist)]: Hey Tapilot, I need some help with preprocessing a dataset. Can you give me a hand? 

[YOU (AI assistant)]: Of course! I'd be happy to help. What's the name of the dataset you're working with? 

[USER (data scientist)]: It's called "credit_customers.csv". Let's start by loading it using pandas. 

[YOU (AI assistant)]: Sure thing! Here's how you can load the dataset using proper functions from decision_company like this:
'''
import pandas as pd 
import pickle
from decision_company import read_csv_file

# Load the dataset 
credit_customers = read_csv_file("credit_customers.csv") 
'''
[USER (data scientist)]: Awesome, now I'd like to know which columns are numerical. Please generate a Series containing the names of numerical columns in the dataset.
My template of code snippet is:

---BEGIN CODE TEMPLATE---

import pandas as pd 
import pickle
from decision_company import read_csv_file, 

# please import the necessary private functions from decision_company first

# Load the dataset 
credit_customers = read_csv_file("credit_customers.csv") 
 
# YOUR SOLUTION BEGIN:
<code1>
[COMPLETE YOUR CODE] 
</code1>
# YOUR SOLUTION END

print("numerical_columns:\n", numerical_columns) 

# save data
pickle.dump(numerical_columns,open("./pred_result/numerical_columns.pkl","wb"))

---END CODE TEMPLATE---

[YOU (AI assistant)]: No problem! You can use proper functions from decision_company to identify the numerical columns. Here's how:
'''
import pandas as pd 
import pickle
from decision_company import read_csv_file, 

# please import the necessary private functions from decision_company first

# Load the dataset 
credit_customers = read_csv_file("credit_customers.csv") 
 
# YOUR SOLUTION BEGIN:
